1

iWork: Analytics for Human Resources Management

Girish Keshav PalshikarTata Consultancy Services Limited54B Hadapsar Industrial Estate, Pune 411013, India.Gk.palshikar@tcs.com

Invited Talk at the Forum for Information Retrieval Evaluation (FIRE 2012), Indian Statistical Institute, Kolkata, India on 19-Dec-2012

2

Human Resources Management HR Management is a crucial function within any

organization– More so in services, IT and BPO industries– HR is a cost center; everyone interacts with HR!

HR function is characterized by a large number of – Business processes– IT systems that automate these business processes– Huge databases of employee activities– Many employee contact initiatives– Close interactions with L&D– Associated metrics and KPI– Monitoring and regulatory compliance

3

Phases in HR Management Talent Acquisition

– Requirement gathering, recruitment planning– Campus recruitment, EP interviews and recruitments

Talent Management and Utilization– Allocation (e.g., to project), team formations, monitoring– Roles and tasks, Utilization tracking (billing, timesheets)– Transfer, deputation, Travel– Training, Knowledge management– Performance appraisal, Promotion, Salary– Communications– Administration (leave, medicals, …)

Talent Retention– Feedback, complaints, grievances, …– Resignation handling, retention, knowledge transfer,

succession

4

Business Goals of HR Management HR is responsible for maintaining a high-quality

workforce – Well-aligned and competitive for the business of the

organization– Effective in performing the business tasks and services,

delivering required value and meeting client expectations;

– Well-trained in the required and emerging skills– Highly responsive to emerging business requirements– Stable (low attrition, low impact of attrition; successful

succession and knowledge transfer)– Cost-effective (low salary and overhead costs)– Able to evolve into leadership– Agile and Mobile (quickly form effective and distributed

teams)– Motivated, high on initiative and ownership, highly

proactive– Happy with their environment, work, roles, salaries,

career paths– Follows professional ethics, codes of conducts etc.– Well-integrated and diverse; highly communicative

5

What Makes HR Management Challenging?

The human factors! Large and varied backgrounds of the workforce Globalization, diversified and distributed workforce New business demands (services, products, …) New business models New customers across the globe Mergers and acquisitions across the globe Changing skills requirements Innovation (disruptive / incremental, technical / domain) Risks (ethical violations, data privacy, client

confidentiality)

6

iWork: Analytics for HR

Data Repositories

Text Repositories

AnalyticsTechniques

InsightsPatterns

Knowledge

Vision• Make effective use of historical databases and document

repositories for solving HR domain-specific problems• Use analytics-driven decision making to meet HR business goals

• Combine data and text mining to build innovative HR domain-specific solutions for significant enterprise

• Deliver analytics-derived to the right users at the right point in the HR business processes

Technology AreasData Mining, Machine Learning, Pattern Recognition, Statistical Analysis,

Natural Language processing, Computational Linguistics, Text Mining; Optimization

HR Domain Knowledge

ActionableNovel

7

iWork: Opportunities Reduce effects of attrition: understanding of root causes,

accurate prediction, targeted retention strategies, backup/replacement plans, …

Improve project team formation: optimal mix of experience and expertise for all projects, optimal cost team, maximize match with associates’ interests

Improve associate satisfaction: better understanding of drivers, identify concrete action items, cost-effective improvement plan, what-if analysis

Talent acquisition: reduce delays and costs, maximize match with requirements, school evaluation, identify patterns of long-term stay, …

Team profiles: in terms of backgrounds, skills, roles, domains, …

Effective RFI Responses/proposals: locate experts, experience, tools

Available HR Datasets: resumes (internal, external), timesheets, project details, in-house tool/document repositories, allocations, trainings, surveys, …

8

iWovierk Overview QUEST: employee/customer survey analytics iRetain: Attrition analytics; retention analytics Resume Center: extract structured information from

resumes; match job requirements; find experts; team skill profiles; …

ExBOS: optimal project team formation iTAG: analytics for talent acquisition Analytics for improving effectiveness of training

programs …

9

iWork Vision: Mine HR data to Drive Improvements to Workforce Management

Talent Acquisition

Talent Utilization and Management

Talent Retention

SPEED

iCALMS

PULSE PEEP

mPOWER

IPMS

Visa Tracker

GESS

HRMSGRS

ExOp

RGS

Workforce

Planning

RMG Tracker

HR Datasets iWork

Complaints Managemen

t System

10

iWork: Strategy and Offerings Build a set of integrated offerings that identify specific improvement

opportunities for Workforce Management Transcend silos in HR systems and data Integrate the offerings with existing HR systems to deliver the

actionable recommendations to the users when they need

• As-is state dashboard for attrition

• Discovering high-attrition groups

• Predictive models for attrition• Identifying root-causes of

attrition• Plan for reducing attrition

impact• Optimal retention plan

Talent Retention

•TA analytics: improve cost, quality, timeliness of TA• ILP analytics

Talent Acquisition• Quest: employee survey analytics• EXBOS: optimal team formation• Visa analytics• Resume Center: competency extraction; find right people for positions; find experts; find misinformation; enrich RFP response (past projects, tools); talent pool profiling; find customer intelligence; • Bench analytics

Talent management

ITIS workforce management: team sizing + shift planning; optimal team skill profile; service level rationalization; expert finding; training plans; DC transformation planning

Automation of survey responses tagging Nielsen

11

Practical Applications Need a Lot More than IR

Various databases and

text repositories

Business Solution

Document retrievals; rankingFine-grained retrievalGoal-directed retrievalPost-processingInformation extractionCross-linking and information fusion (e.g., with FB, LinkedIn)ClassificationVisualization;SummarizationAnalytics (problem-specific)Learning to rank

12

RESUME CENTER

Effective use of resumes in all HR functions

13

Using Resumes in HR Functions Resumes: a valuable source of information for people’s work

– ~250,000 TCS employees’ resumes– ~2 million candidates’ (applicants’) resumes

Business goals– Use information extraction: extract personal, job history,

project details, education, training, awards etc. from given resumeso Validate information in resumeso Create gazettes (colleges, degrees, certifications, tools,

companies)– Update employee experience profile and skills/competencies – Identify top K best matches for a given job requirement /

position o Learning to rank (poster in FIRE 2012)o improve team formation; shorten recruitment cycle

– Perform mining of data extracted from resumes to derive novel, actionable insights about the available talent poolo reduce bench; reduce attrition; improve utilizationo identify training opportunities; help in career planning

14

Resume Center: Information Extraction

On-the-fly extraction using an IR engine

15

Resume Center: Information Extraction

16

Resume Center: PowerMiner Given a set of resumes, provide facilities to help in filing

RFI/RFP responses, form project teams etc. locate relevant projects for a given project description locate relevant tools for a given project description identify expert persons for a given technical area assign domain(s) to each resume (e.g., insurance,

railways, banking, telecom etc.) Identify "unusually high quality" resumes in terms of a

set of pre-defined quality criteria – Special tools, niche skills, extra qualifications (e.g.,

domain-related), top-quality academic performance, awards, publications

17

Resume Center: Team Profiler Given a resume repository, help HR executives in

building an “understanding” of their teams:– What are the strengths and weaknesses of my team in

terms of technical skills, domain knowledge, roles etc.? – What should I do to improve the quality of my teams?

Create a summary profile of a team, in terms of technology skills, domains, experience etc.;

Group the given resumes into clusters (from different perspectives), with specific interpretation for each cluster– Similar to customer segmentation?

Document repository visualization and exploratory facilities

18

R. Srivastava, G. K. Palshikar, RINX: Information Extraction, Search and Insights from Resumes, Proc. TCS Technical Architects' Conf., (TACTiCS 2011), Thiruvanthapuram, India, Apr. 2011.

S. Pawar, R. Srivastava, G.K. Palshikar, Automatic Gazette Creation for Named Entity Recognition and Application to Resume Processing, Proc. ACM COMPUTE 2012 Conference, Pune, India, 24-Jan-2012.

G.K. Palshikar, R. Srivastava, S. Pawar, Delivering Value from Resume Repositories, TCS White Paper published on www.tcs.com, Feb. 2012. (c) Tata Consultancy Services Limited.

19

QUESTSurvey response analytics

20

QUEST: Overview Advanced analytics tool to mine survey response data and

derive novel, actionable insights for improving workforce management

Surveys are a direct and effective mechanism to gauge concerns and issues that affect satisfaction of employees or customers

Motivation: TCS conducts an annual in-house employee survey– 250,000 employees, ~100 questions (structured, free-form) – 250,000 textual responses to each of ~20 questions– Challenges: volumes; dependencies; mixed structured/text

responses Business goals: improve satisfaction levels among

employees Benefits: deeper insights, objective results, reduced

time/efforts Impact: Satisfaction levels affect projects quality, client

satisfaction Status: Currently deployed in-house Vision

– QUEST should be an integral part of all HR contact and feedback programs throughout TCS (ISU, geographies, clients etc.)

– Deploy for customer / product satisfaction surveys

21

QUEST: Approach Dashboards and standard reports Drill-down exploratory analysis Visualization Summarize responses to specific questions/categories Identify specific issues, concerns and suggestions Characterize low-satisfaction groups (discover common

characteristics of employees with high/low satisfaction) Identify factors (root causes) that affect satisfaction Design optimal plans to improve satisfaction levels Use survey results in team planning and other

workforce management tasksG.K. Palshikar, S. Deshpande, S. Bhat, QUEST: Discovering Insights from Survey Responses, Proc. 8th Australasian Data Mining Conf. (AusDM09), Dec. 1-4, 2009, Melbourne, Australia, P.J. Kennedy, K.-L. Ong, P. Christen (Ed.s), CRPIT, vol. 101, published by Australian Computer Society, pp. 83 - 92, 2009.

22

QUEST: Results

23

QUEST: Results…Things you don’t like about TCS

24

Quest: Results…

Groups having unusually low ASIEXPERIENCE_RANGE = ‘4-7’ (60.4; global avg. = 73.8)Root causes for low ASICanteen, Transportation, RMG

PULSE 2008-09 Responses for TCS Mumbai

M. Natu, G.K. Palshikar, Interesting Subset Discovery and its Application on Service Processes, Proc. Workshop on Data Mining for Services (DMS 2010) held as part of the Int. Conference on Data Mining (ICDM 2010), Australia, 2010, pp. 1061-1068.

Interesting subset discovery: finding bumps in a large-dimensional distribution

25

QUEST: Results…

Actionable suggestions made by associatesTCS can have tie ups with best Schools in the near by locations for their employee kids… the moment you step out there is only garbage and randomly parked autos aroundTCS can engage with lease agreement … with TATA Housing itself and provide economical accommodation.I don`t have any leg space...n my knees are hurting badly

S. Deshpande, G.K. Palshilkar, G Athiappan, An Unsupervised Approach to Sentence Classification, Proc. Int. Conf. on Management of Data (COMAD 2010), Nagpur, 2010, Allied PublishersPvt. Ltd., pp. 88 - 99.

26

Sentence Classification

Sentence class labels are usually domain-dependent

Unsupervised classification of sentences: specific / general

27

Sentence Classification…

A SPECIFIC sentence is more ”on the ground”

A GENERAL sentence is more ”in the air” Example:

– My table is cramped and hurts my knees. – The work environment needs improvement.

– Travel vouchers should be cleared within 2 working days.

– Accounts department is very inefficient.

28

Sentence Classification… Compute a specificity score for each sentence:

– Unsupervised (knowledge-based), without the need for any labeled training examples.

– Define a set of features and compute their values for each sentence.

– The features are lexical / semantic. – The features are context-free: their values are

computed exclusively using the words in the sentence and do not depend on any other (e.g., previous) sentences.

– Then combine the feature values for a particular sentence into its specificity score.

Rank the sentences in terms of their specificity score.

29

Sentence Classification…

Sentence features– Average semantic depth (ASD)– Average semantic height (ASH)– Total occurrence count (TOC)– Count of Named Entities (CNE)– Count of Proper Nouns (CPN)– Sentence Length (LEN)

30

Sentence Classification…

Semantic depth (SD) SDT(w) of a word w is the distance (number of edges) from the root of ontology T to word w in T– We use T = WordNet ISA ontology– More semantic depth more specific word

31

Sentence Classification…

Semantic depth of a word changes with its POS tag and with its sense; – SD(bank) = 7 for financial institution– SD(bank) = 10 for flight maneuver sense.

Solution:– Apply word sense disambiguation (WSD)

during pre-processing; or– Take average of the semantic depths of

the word for top k of its senses

32

Average semantic depth S.ASD for a sentence S = <w1 w2 . . . wn> containing n content-carrying words = the average of the semantic depths of the individual words

My table hurts the knees. – (8 + 2 + 6)/3 = 5.3

The work environment needs improvement.– (6 + 6 + 1 + 7)/4 = 5.

33

Semantic height (SH) SHT(w) of a word w is the length of the longest path in T from word w to a leaf node– We use T = WordNet hyponym ontology– Lower semantic height more specific word

34

Average semantic height S.ASH for a sentence S = <w1 w2 . . . wn> containing n content-carrying words (non stop-words) = the average of the semantic heights of the individual words

Semantic height of a word changes with its POS tag and with its sense;

Solution: use WSD or take average of the semantic heights of the word for top k of its senses

35

Intuition: more specific sentences tend to include words which occur rarely in some reference corpus– apple (2), fruit (14), food (34)

More the number of rare words in a sentence, more specific it is likely to be.

OC(w) = occurrence count of word w in WordNet; – if w has multiple senses, then OC(w) = average of the

occurrence counts for top k senses of w Total occurrence count S.TOC for a sentence S =

<w1 w2 ... wn> containing n content words is the sum of the lowest m occurrence counts of the individual words, where m is a fixed value (e.g., m = 3).

OC of a word changes with its POS tag and with its sense;

Solution: use WSD or take average of the OC of the word for top k of its senses

36

Named entities (NE) are commonly occurring groups of words which indicate specific semantic content – Person name (e.g., Bill Gates) – Organization name (e.g., Microsoft Inc.), – location (e.g., New York), – date, time, amount, email addresses etc.

Since each NE refers to a particular object, an NE is a good indicator that the sentence contains specific information.

Another feature S.CNE for a sentence S is the count of NE occurring in S

37

Proper Nouns (PN) are commonly occurring groups of words which indicate specific semantic content – Abbreviation (IBM or kg), domain terms

(oxidoreductases), words like (Apple iPhone), numbers etc.

Since each PN may refer to a particular object, an PN is a good indicator that the sentence contains specific information.

Another feature S.CPN for a sentence S is the count of PN occurring in S

38

Sentence length, denoted S.Len, is a weak indicator of its specificity in the sense that more specific sentences tend to be somewhat longer than more general sentences.

Length refers to the number of content carrying words (not stopwords) in the sentence, including numbers, proper nouns, adjectives and adverbs

39

Features have contradictory polarity. – We want higher values more specificity.– Not true for features ASH and TOC– Lower values higher specificity for these

Scales of values for various features are not the same, because of which some features may unduly influence the overall combined score. – E.g., ASD is usually 10, whereas TOC is a

larger integer. Uniform scaling: map x[a, b] to y [c, d]

Scaling + reversal of polarity

40

41

42

Sentences 6, 7, 9 as top 3 in terms of specificity score

43

Some specific sentences identified by our algorithm from 110,000 responses in an employee satisfaction survey

44

Some specific sentences identified by our algorithm from 220 sentences from 32 reviews of a hiking backpack product by Kelty.

45

Conclusions

Domain-driven IR = IR + text-mining of retrieved documents

Enterprise document repositories offer good scope for Domain-driven IR to deliver solutions and insights relevant for real-life business problems and decisions